Performance Degradation after source build inside Docker on Intel i7-5820K CPU

[sandonair007]

Hi there, I am using nGraph to accelerate my model.

As my cpu is not Xeon series, I built nGraph and tensorflow from source inside Docker following Option 2 in README. The build succeeded and pass the model test. However, the inference time is much more slower when using nGraph backend.

CPU: 0.03387284278869629 secs
NGRAPH_CPU: 0.11669778823852539 secs

Could anyone point out possible reason for this?

Btw, I notice there are setting recommendations for Xeon series. (https://ngraph.nervanasys.com/docs/latest/frameworks/generic-configs.html#ngraph-enabled-intel-xeon.) I am wondering if the environment parameter settings would affect a lot.

Any hint is highly appreciated!!

[avijit-nervana]

What DL model you tried for this test?

[sandonair007]

I am using a simple model trained on mnist. The model file is borrowed from https://github.com/nex3z/tfmobile-mnist-android. The session is run for multiple times.